Before we get to see Volta in action NVIDIA is taking a half step and releasing the Pascal architecture which will use Maxwell-like Streaming Multiprocessors and will introduce stacked or 3D memory which will reside on the same substrate as the GPU. Jen-Hsun claimed this new type of memory will vastly increase the bandwidth available, provide two and a half times the capacity and be four times as energy efficient at the same time. Along with the 3D memory announcement was the revealing of NVLink, an alternative interconnect which he claims will offer 5-12 times the bandwidth of PCIe and will be utilized by HPC systems. From his announcement that NVLink will feature eight 20Gbps lanes per block or as NVIDIA is calling them, bricks, which The Tech Report used to make a quick calculation and came up with an aggregate bandwidth of a brick of around 20GB/s. Read on to see what else was revealed.
"Today during his opening keynote at the Nvidia GPU Technology Conference, CEO Jen-Hsun Huang offered an update to Nvidia's GPU roadmap. The big reveal was about a GPU code-named Pascal, which will be a generation beyond the still-being-introduced Maxwell architecture in the firm's plans."
Here is some more Tech News from around the web:
- Nvidia, VMware join to pipe high-quality 3D graphics from the cloud @ The Register
- Android has 97 Percent of Mobile Malware, But Nearly None in the U.S. @ DailyTech
- Amazon HALVES cloud storage prices after Google's shock slash @ The Register
- Bitcoin mining malware hits Android @ The Inquirer
- Facebook Oculus VR buy causes rift with developers and tech fans @ The Inquirer
- iSAW EXtreme Action Camera @ Kitguru
- Netgear VueZone VZSX2800 Wireless Surveillance Camera Kit @ eTeknix
Before we get to see Volta in
Before we get to see Volta in action NVIDIA is taking a half step and releasing the Pascal architecture which will use Maxwell-like Streaming Multiprocessors and will introduce stacked or 3D memory which will reside on the same substrate as the GPU.
Pretty sure based on everything we knew about Volta from a year ago, Pascal is just a replacement codename. The details look practically the same (Unified Memory, Stacked memory) with the only new addition in details being NVLink.
Still speculation that Einstein (previous codename to come out after Maxwell) also got scrapped some years ago, or it may be a complete merging of Nvidia’s Exascale computing due in 2018 on 10nm.
Pascal is still on the
Pascal is still on the roadmap with no release date so it is possible it will fall by the wayside. At this point though NVIDIA still seems to be planning to release Pascal sometime in the future.
NvLink is just CAPI –
NvLink is just CAPI – Coherent Accelerator Processor Interface, renamed!
See the IBM founded OpenPOWER Foundation (Formally called “OpenPOWER Consortium”) Nivida is in with IBM and Others, so Like AMD’s marketing hijacking the generic term HSA as a buzzword, Nvidia just Renames CAPI to NVLink, pure marketing BS at work here! The same goes for LightPeak to Thunderbolt, as well as other technology renamining to give credit where credit is not dew! look for others to implement this technology, with equally ridiculous marketing terms!
HSA was around long before AMD abused the term, so do not equate AMD’s HSA implementation and use of the term with Anyone else’s HSA implementation of HSA, and everyone will have a version of HSA, just like everyone will have a version of CAPI! Oh those open standards renamed by the marketing monkeys just to make their companies look innovative!